© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8278
    Prev
    Next
    INDEX
    Explanations

    regulatory aspects, decisions, guidance, policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tracks
    -0.09
    worm
    -0.09
    OfString
    -0.09
    anken
    -0.08
    ness
    -0.08
    /array
    -0.08
     Osman
    -0.08
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
    arity
    -0.08
    еÑģ
    -0.08
    POSITIVE LOGITS
    ä½ĵç³»
    0.12
    .microsoft
    0.10
    yı
    0.09
    quot
    0.09
    ä½ĵ系建设
    0.09
    ourke
    0.08
    åij½
    0.08
    å¾Ĺä½ı
    0.08
    ãĥ¼ãĤ
    0.08
    ather
    0.08
    Activations Density 0.013%

    No Known Activations